Interpretability & Mechanistic Analysis

Interpretability & Mechanistic Analysis

dynaxx on the hidden graph: interpretability via circuit-level abstraction

This comprehensive guide explores the emerging paradigm of circuit-level abstraction for understanding neural networks, moving beyond neuron-level int...

Interpretability & Mechanistic Analysis

The Dynaxx Mechanistic Audit: Tracing Causal Paths in Production Models

This comprehensive guide explores the Dynaxx Mechanistic Audit, a rigorous methodology for tracing causal paths in production models. Unlike conventio...

Interpretability & Mechanistic Analysis

The dynaxx map: tracing feature superposition to latent circuit topology

Introduction: The Problem of Feature SuperpositionWhen we inspect the internal representations of a deep neural network, we often find that individual...

Interpretability & Mechanistic Analysis

Dynaxx on the Circuitry Frontier: Mechanistic Probes for Superposition and Polysemanticity

Introduction: The Black Box is a MirageIn my decade of working with deep learning systems, first in academic research and now leading the Dynaxx resea...

Interpretability & Mechanistic Analysis

The Dynaxx Dissection: Reverse-Engineering In-Context Learning as Implicit Gradient Descent

Introduction: The Black Box That Changed EverythingWhen I first encountered GPT-3's ability to perform a novel task from just a few examples in a prom...